CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

status

Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is exemplary: two copy-paste-ready diagnostic commands, precise reporting instructions constrained to actual JSON fields, and an explicit authentication-failure branch with recovery advice. It is lean, fully executable, and correctly sized with no unnecessary bundle files.

DimensionReasoningScore

Conciseness

The ~20-line body is lean with zero padding: no explanation of what Mem0 is, no filler, and every line adds non-obvious information such as "`flushes` is the number of completed flushes, not a pending count" and "Never report an auth failure as 'no memories found'". This matches anchor 5 — every token earns its place.

5 / 5

Actionability

Two fully executable, copy-paste-ready commands (`memory_cli.py ... status --json` and `... doctor`) are given, plus exact instructions on which JSON fields to report and an explicit failure-case playbook: "If doctor reports an authentication failure (401 / invalid key), say clearly that the Mem0 API key is invalid or expired... Suggest reinstalling with `--config api_key=...`". This matches anchor 5 — executable commands covering the common cases including failure handling.

5 / 5

Workflow Clarity

For this simple single-purpose skill the sequence is unambiguous: run both commands, summarize using only fields the JSON actually reports, and branch on auth failure with recovery guidance. The "using only fields the JSON actually reports" instruction and the explicit 401 handling serve as validation checkpoints, matching the rubric's simple-skill allowance for a score of 5; the destructive-operation cap does not apply since the skill is read-only diagnostics.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references — verified that no references/, scripts/, or assets/ files exist in the bundle. Nothing that belongs in a separate file is inlined; the body is appropriately self-contained and well organized, matching the rubric's guidance that such skills can score 5.

5 / 5

Total

20

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it clearly and explicitly states both what the skill does (with four concrete diagnostic facets) and when to use it, in natural third-person trigger phrasing. The only weaknesses are the broad "anything looks broken" clause, which slightly widens conflict risk, and missing trigger synonyms.

DimensionReasoningScore

Specificity

The description names the domain ("Show whether Mem0 memory is working in this repository") and enumerates four concrete facets: "configuration, capture state, pending flushes, and whether the Mem0 API key is valid". It lists several specific capabilities with minor gaps rather than a comprehensive set of distinct actions, matching anchor 4 — above anchor 3 (only 1-2 concrete actions) but below anchor 5 (comprehensive multi-action coverage).

4 / 5

Completeness

It explicitly answers both "what" ("Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid") and "when" ("Use when the user asks whether memory is on, why a memory is missing, or anything looks broken") with concrete trigger phrases, exactly matching anchor 5.

5 / 5

Trigger Term Quality

The trigger clause "Use when the user asks whether memory is on, why a memory is missing, or anything looks broken" contains natural phrases users would actually say. Coverage is good but misses common variations like "memories not saving", "is memory working", or "memory not storing", matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche is clear ("Mem0 memory is working in this repository") with memory-scoped triggers, but the clause "or anything looks broken" is a broad generic trigger that could fire on unrelated breakage, creating minor overlap risk — anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mem0ai/mem0

Path

integrations/mem0-agent-plugin/skills/status/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.